Change search
ReferencesLink to record
Permanent link

Direct link
The Support Betting Vector Machine: A quantitative approach on beating the betting market.
Umeå University, Faculty of Social Sciences, Umeå School of Business and Economics (USBE), Statistics.
2016 (English)Independent thesis Advanced level (degree of Master (One Year)), 10 credits / 15 HE creditsStudent thesisAlternative title
The Support Betting Vector Machine : kvantitativ studie om möjlighet att slå spelmarknaden. (Swedish)
Abstract [en]

The Support Betting Vector Machine has explored the possibility to beat the betting market by generating a positive return on investment (ROI). 6460 games from Premier League (UK) were used to predict if games would result in over or under 2.5 goals. For classication, Support Vector Machine was used with appliance of a method to get class probabilities. The class probabilities were used together with the betting strategy Kelly Criterion to determine if the predictions were suitable to bet on, in regards to generating a long term positive ROI. However, it was showed that Kelly Criterion was not suitable, and a simpler betting system was used, were one constant used was placed. Logistic Regression showed the best result, with a ROI of 3.9 percent.

Place, publisher, year, edition, pages
National Category
Probability Theory and Statistics
URN: urn:nbn:se:umu:diva-122688OAI: diva2:940552
Available from: 2016-06-21 Created: 2016-06-21 Last updated: 2016-06-21Bibliographically approved

Open Access in DiVA

No full text

By organisation
Probability Theory and Statistics

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 22 hits
ReferencesLink to record
Permanent link

Direct link